CoverIntent

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare write/idempotent/non-destructive/non-open-world; the description adds substantive context beyond them — the capture is public and quarantined, not sellable, and remains gated until a later authenticated original-session mandate is validated. It also signals the payload must be non-identifying. It does not describe retry/duplicate behavior despite idempotentHint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences: the action and its scope come first, followed by the operational prohibition and the downstream consequence. Nothing is repeated from the schema and no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation. The description covers the origin constraint, the privacy constraint, and the lifecycle status of the record, which are the non-obvious things an agent must know. Minor gap: nothing on duplicate/idempotent retry outcomes or what to do when the origin session secret is unavailable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 60% and three of the five top-level parameters already carry descriptions (agent handle, idempotency key, session commitment). The description reinforces the semantic constraints on those — 'non-identifying' and 'exact ... from the same AI session' — but adds no detail on the nested intent fields beyond what enums convey. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (capture) and a specific resource (a non-identifying Nevada personal-auto insurance intent from the current AI session). The scope is narrow and unambiguous. It stops short of 5 only because there are no siblings to distinguish from and the term 'intent candidate' is left to the schema to explain.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'from the same AI session in which a human asked for insurance help' plus 'Do not ask the human to repeat the request' gives an implicit trigger: call it at the point of the human request, not in a later session. However, no explicit when-not-to-call condition or failure handling (e.g., what to do if origin is unknown) is stated, and there are no siblings to route against.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.